1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
|
from __future__ import annotations
from sqlglot import exp, transforms
from sqlglot.dialects.dialect import parse_date_delta
from sqlglot.dialects.spark import Spark
from sqlglot.dialects.tsql import generate_date_delta_with_unit_sql
from sqlglot.tokens import TokenType
class Databricks(Spark):
class Parser(Spark.Parser):
LOG_DEFAULTS_TO_LN = True
FUNCTIONS = {
**Spark.Parser.FUNCTIONS,
"DATEADD": parse_date_delta(exp.DateAdd),
"DATE_ADD": parse_date_delta(exp.DateAdd),
"DATEDIFF": parse_date_delta(exp.DateDiff),
}
FACTOR = {
**Spark.Parser.FACTOR,
TokenType.COLON: exp.JSONExtract,
}
class Generator(Spark.Generator):
TRANSFORMS = {
**Spark.Generator.TRANSFORMS, # type: ignore
exp.DateAdd: generate_date_delta_with_unit_sql,
exp.DateDiff: generate_date_delta_with_unit_sql,
exp.JSONExtract: lambda self, e: self.binary(e, ":"),
exp.Select: transforms.preprocess(
[
transforms.eliminate_distinct_on,
transforms.unnest_to_explode,
]
),
exp.ToChar: lambda self, e: self.function_fallback_sql(e),
}
PARAMETER_TOKEN = "$"
class Tokenizer(Spark.Tokenizer):
HEX_STRINGS = []
SINGLE_TOKENS = {
**Spark.Tokenizer.SINGLE_TOKENS,
"$": TokenType.PARAMETER,
}
|
